Search Results (27)

Fibrous dysplasia is one of the most common skeletal lesions. The wide spectrum of clinical manifestations ranges from asymptomatic conditions (typical of monostotic forms) to severe skeletal diseases with deformity and fractures for polyostotic fibrous dysplasia. The classical radiological features include: an osteolytic geographic pattern, ground-glass bone matrix, cortical thinning/cortical scalloping, bone deformities and enlargement, concavity of margins (evaluated with MRI), and cystic areas (MRI). All the bones can be affected, and the proximal femur is the most common one (about 30% of cases). Nonetheless, the disease can also affect cranio-facial bones, leading to compression of neural structures, as well as deformation and enlargement of facial bones, leading to the so-called “leontiasis ossea” or “facies leonine”. The polyostotic forms of fibrous dysplasia can be associated with multiple soft-tissue myomas (Mazabraud syndrome) or several endocrine diseases (McCune–Albright syndrome). In every diagnostic step of the disease, as well as in different fibrous dysplasia forms, imaging plays a key role. Indeed, radiology is fundamental to assess the suspicion of fibrous dysplasia in classical monostotic forms, representing the sole diagnostic tool needed in many cases. Imaging is also fundamental to staging and following up on more severe polyostotic forms, as well as for detecting complications. In this comprehensive updated review article, we examine every aspect of the disease, with a main focus on imaging presentation. The indications for biopsy are discussed as well. Most importantly, the article details the potential risk of malignant transformation (osteosarcoma, fibrosarcoma, chondrosarcoma, and other rarer sarcomas, all accounting for <1% of cases) underlying the radiological patterns of these conditions. The occurrence of aneurysmal bone cyst-like changes on fibrous dysplasia is also analyzed in the article. This review article aims to be a comprehensive guide for radiologists and clinicians involved in the care of patients affected by various forms of fibrous dysplasia, and a starting point for future research. Many classical and atypical cases are collected as an iconographic comprehensive representation. Full article

Mastication and swallowing are complex physiological processes involving the coordinated activity of multiple tissues in the oral cavity, facial region, and laryngeal system. Some detection methods suffer from limitations such as insufficient information acquisition and inadequate temporal feature analysis. To address these issues, this study proposes a conceptual method for analyzing the state of masticatory and swallowing movements. It integrates maxillofacial electromyographic (EMG) signals with laryngeal movement signals. The goal is to preliminarily explore state analysis of masticatory and swallowing movements over time. A designed gain-adjustable conditioning circuit processes and acquires these signals: maxillofacial EMG signals from EMG electrodes and laryngeal movement signals from flexible PVDF piezoelectric sensors. These two signal streams complement each other’s missing information, enabling comprehensive detection of the state of masticatory and swallowing movements. To address time-point labeling in mastication and swallowing, a sliding-window-based dispersion calculation method was employed to extract characteristic signal nodes, which were then accurately associated with their corresponding physiological motion states. We combined temporal features such as the zero point, onset of fluctuations, characteristic peaks, and baseline recovery from electromyographic (EMG) signals and laryngeal movement signals. This allowed us to establish a correspondence between key time points in the mastication and swallowing processes. The coefficient of determination (R²) for the pressure–voltage linear fit of the PVDF flexible piezoelectric sensor was 0.99446. The pressure resolution was approximately 0.08 kPa. Response times were no more than 15 ms for the EMG channel and no more than 10 ms for the PVDF pressure channel. These results indicate that this method is feasible for extracting oral movement time parameters in healthy subjects. Full article

Examinations are typically used by educational institutions to assess students’ strengths and weaknesses. Unfortunately, exam malpractices like cheating and other forms of academic integrity violations continue to present a serious challenge to the evaluation framework because it seeks to provide a trustworthy assessment. Existing methods involving human invigilators have limitations, as they must be physically present in examination settings and cannot monitor all students who take an exam while successfully ensuring integrity. With the developments in artificial intelligence (AI) and computer vision, we now have novel possibilities to develop methods for detecting students who engage in cheating. This paper presents a practical, real-time detection system based on computer vision techniques for detecting cheating in examination halls. The system utilizes two primary methods: The first method is YOLOv8, a top-of-the-line object detection model, where the model is used to detect students in video footage in real time. After detecting the students, the second aspect of the detection process is to apply pose estimation to extract key points of the detected students. For the first time, this paper proposes to measure angles from the geometry of the key points of detected students by constructing two triangles using the distance from the tip of the nose to both eyes, and the distance from the tip of the nose to both ears; one triangle is sized from the distance to the eyes, and the other triangle contains the measurements to their ears. By continually calculating these angles, it is possible to derive each student’s facial pose. A dynamic threshold is calculated and updated for each frame to better represent the body position in real time. When the left or right angle pass that threshold, it is flagged as suspicious behavior indicating cheating. All detected cheating instances, including duration, timestamps, and captured images, are logged automatically in an Excel file stored on Google Drive. The proposed study presents a computationally cheap approach that does not utilize a GPU or additional computational aspects in any capacity. This implementation is affordable and has higher accuracy than all of those mentioned in prior studies. Analyzing data from exam halls indicated that the proposed system reached 96.18% accuracy and 96.2% precision. Full article

Driver fatigue is a primary factor in traffic accidents and poses a serious threat to road safety. To address this issue, this paper proposes a multi-feature fusion fatigue detection method based on an improved YOLOv8 model. First, the method uses an enhanced YOLOv8 model to achieve high-precision face detection. Then, it crops the detected face regions. Next, the lightweight PFLD (Practical Facial Landmark Detector) model performs keypoint detection on the cropped images, extracting 68 facial feature points and calculating key indicators related to fatigue status. These indicators include the eye aspect ratio (EAR), eyelid closure percentage (PERCLOS), mouth aspect ratio (MAR), and head posture ratio (HPR). To mitigate the impact of individual differences on detection accuracy, the paper introduces a novel sliding window model that combines a dynamic threshold adjustment strategy with an exponential weighted moving average (EWMA) algorithm. Based on this framework, blink frequency (BF), yawn frequency (YF), and nod frequency (NF) are calculated to extract time-series behavioral features related to fatigue. Finally, the driver’s fatigue state is determined using a comprehensive fatigue assessment algorithm. Experimental results on the WIDER FACE and YAWDD datasets demonstrate this method’s significant advantages in improving detection accuracy and computational efficiency. By striking a better balance between real-time performance and accuracy, the proposed method shows promise for real-world driving applications. Full article

Meme image sentiment analysis is a task of examining public opinion based on meme images posted on social media. In various fields, stakeholders often need to quickly and accurately determine the sentiment of memes from large amounts of available data. Therefore, innovation is needed in image pre-processing so that an increase in performance metrics, especially accuracy, can be obtained in improving the classification of meme image sentiment. This is because sentiment classification using human face datasets yields higher accuracy than using meme images. This research aims to develop a sentiment analysis model for meme images based on key points. The analyzed meme images contain human faces. The facial features extracted using key points are the eyebrows, eyes, and mouth. In the proposed method, key points of facial features are represented in the form of graphs, specifically directed graphs, weighted graphs, or weighted directed graphs. These graph representations of key points are then used to build a sentiment analysis model based on a Deep Neural Network (DNN) with three layers (hidden layer: i = 64, j = 64, k = 90). There are several contributions of this study, namely developing a human facial sentiment detection model using key points, representing key points as various graphs, and constructing a meme dataset with Indonesian text. The proposed model is evaluated using several metrics, namely accuracy, precision, recall, and F-1 score. Furthermore, a comparative analysis is conducted to evaluate the performance of the proposed model against existing approaches. The experimental results show that the proposed model, which utilized the directed graph representation of key points, obtained the highest accuracy at 83% and F1 score at 81%, respectively. Full article

Secure authentication in smart device ecosystems remains a critical challenge, particularly due to the irrevocability of compromised biometric templates in server-based systems. This paper presents a post-quantum secure multi-factor authentication protocol that combines templateless 2D and 3D facial biometrics, liveness detection, and Physical Unclonable Functions (PUFs) to achieve robust identity assurance. The protocol exhibits zero-knowledge properties, preventing adversaries from identifying whether authentication failure is due to the biometric, password, PUF, or liveness factor. The proposed protocol utilizes advanced facial landmark detection via dlib or mediapipe, capturing multi-angle facial data and mapping it. By applying a double-masking technique and measuring distances between randomized points, stabilized facial landmarks are selected through multiple images captured during enrollment to ensure template stability. The protocol creates high-entropy cryptographic keys, securely erasing all raw biometric data and sensitive keys immediately after processing. All key cryptographic operations and challenge-response exchanges employ post-quantum algorithms, providing resistance to both classical and quantum adversaries. To further enhance reliability, advanced error-correction methods mitigate noise in biometric and PUF responses, resulting in minimal FAR and FRR that meets industrial standards and resilience against spoofing. Our experimental results demonstrate this protocol’s suitability for smart devices and IoT deployments requiring high-assurance, scalable, and quantum-resistant authentication. Full article

Background: Skull base tumors can extend into the temporal bone and occasionally even be visible through the tympanic membrane (TM) if they grow into the middle ear cavity. The differential diagnosis of a skull base mass is extensive and ranges from non-tumorous lesions like cholesteatoma to benign tumors like schwannoma and to malignant lesions like metastatic cancer. Optical coherence tomography (OCT) is a noninvasive imaging technique that can image tissue with high resolution in three dimensions, including through structures such as the TM and bone. OCT angiography is also able to assess tissue vascularity. We hypothesized that OCT could help shrink the differential diagnosis in clinic on the day of initial presentation. Specifically, we thought that OCT angiography could help distinguish between highly vascular skull base tumors such as glomus jugulare and other less vascular tumors and middle ear pathologies such as cholesteatoma and schwannoma. Objectives: We sought to determine whether OCT can image through the TM in clinic to distinguish a normal ear from an ear with a mass behind the tympanic membrane. Furthermore, we sought to assess whether OCT angiography can detect vascularity in these masses to help inform the diagnosis. Methods: We designed and built a custom handheld OCT system that can be used like an otoscope in clinic. It is based off a 200 kHz swept-source laser with a center wavelength of 1310 nm and a bandwidth of 39 nm. It provides a 33.4 μm axial and 38 μm lateral resolution. Cross-sectional images of the middle ear space, including OCT angiography, were captured in an academic neurotology clinic. Patients with normal ear exams, glomus tumors, cholesteatomas, and facial nerve schwannoma were imaged. Results: OCT images revealed key structures within the middle ear space, including the TM, ossicles (malleus and incudostapedial joint), chorda tympani, and cochlear promontory. OCT also identified middle ear pathology (using pixel intensity ratio in the middle ear normalized to the TM) when compared with patients with normal ear exams (mean 0.082, n = 6), in all patients with a glomus tumor (mean 0.620, n = 6, p < 0.001), cholesteatoma (mean 0.153, n = 4, p < 0.01), and facial nerve schwannoma (0.573, n = 1). OCT angiography revealed significant vascularity within glomus tumors (mean 1.881, n = 3), but minimal vascularity was found in normal ears (mean 0.615, n = 3, p < 0.05) and ears with cholesteatoma (mean 0.709, n = 3, p < 0.01), as expected. Conclusions: OCT is able to image through the TM and detect middle ear masses. OCT angiography correctly assesses the vascularity within these masses. Thus, OCT permits the clinician to have additional point-of-care data that can help make the correct diagnosis. Full article

Accurate measurement of frontomaxillary facial (FMF) angles in prenatal ultrasound (US) scans plays a pivotal role in the screening of trisomy 21. Nevertheless, this intricate procedure heavily relies on the proficiency of the ultrasonographer and tends to be a time-intensive task. Furthermore, FMF angles are subjective when measured manually. To address this challenge, we propose a deep learning-based assisted examination framework for automatically measuring FMF angles on 2D ultrasound images. Firstly, we trained a deep learning network using 1549 fetal ultrasound images to achieve automatic and accurate segmentation of critical areas. Subsequently, a key point detection network was employed to predict the coordinates of the requisite points for calculating FMF angles. Finally, FMF angles were obtained through computational means. We employed Pearson correlation coefficients and Bland–Altman plots to assess the correlation and consistency between the model’s predictions and manual measurements. Notably, our method exhibited a mean absolute error of 2.354°, outperforming the typical standards of the junior expert. This indicates the high degree of accuracy and reliability achieved by our approach. Full article

Background: Unilateral condylar hyperplasia (UCH) is characterized by slow progression and enlargement of the condyle, accompanied by elongation of the mandibular body, resulting in facial asymmetry, occlusal disharmony, and joint dysfunction. This condition can be defined as “active” or “inactive”: the active form is characterized by continuous growth and dynamic histologic changes, whereas the inactive form indicates that the growth process has stabilized. Since there are few microscopic studies on the inactive form, this study aims to investigate the histological features and expression of key proteins and bone markers in patients diagnosed with inactive UCH. Methods: A total of 15 biopsies from patients aged 28 to 36 years were examined by light microscopy and immunofluorescence for collagen I and II, metalloproteinases 2 (MMP-2) and 9 (MMP-9), receptor activator of nuclear factor- kappa B (RANK), and osteocalcin. Results: Our findings indicate that during inactive UCH, the ongoing process is not entirely stopped, with moderate expression of collagen, metalloproteinases, RANK, and osteocalcin, although no cartilage islands are detectable. Conclusions: The present study shows that even if these features are moderate when compared to active UCH and without cartilage islands, inactive UCH could be characterized by borderline features that could represent an important trigger-point to possible reactivation, or they could represent a long slow progression that is not “self-limited”. Full article

Convolutional neural networks have made significant progress in human Facial Expression Recognition (FER). However, they still face challenges in effectively focusing on and extracting facial features. Recent research has turned to attention mechanisms to address this issue, focusing primarily on local feature details rather than overall facial features. Building upon the classical Convolutional Block Attention Module (CBAM), this paper introduces a novel Parallel Hybrid Attention Model, termed PH-CBAM. This model employs split-channel attention to enhance the extraction of key features while maintaining a minimal parameter count. The proposed model enables the network to emphasize relevant details during expression classification. Heatmap analysis demonstrates that PH-CBAM effectively highlights key facial information. By employing a multimodal extraction approach in the initial image feature extraction phase, the network structure captures various facial features. The algorithm integrates a residual network and the MISH activation function to create a multi-feature extraction network, addressing issues such as gradient vanishing and negative gradient zero point in residual transmission. This enhances the retention of valuable information and facilitates information flow between key image details and target images. Evaluation on benchmark datasets FER2013, CK+, and Bigfer2013 yielded accuracies of 68.82%, 97.13%, and 72.31%, respectively. Comparison with mainstream network models on FER2013 and CK+ datasets demonstrates the efficiency of the PH-CBAM model, with comparable accuracy to current advanced models, showcasing its effectiveness in emotion detection. Full article

Fatigue driving is a serious threat to road safety, which is why accurately identifying fatigue driving behavior and warning drivers in time are of great significance in improving traffic safety. However, accurately recognizing fatigue driving is still challenging due to large intra-class variations in facial expression, continuity of behaviors, and illumination conditions. A fatigue driving recognition method based on feature parameter images and a residual Swin Transformer is proposed in this paper. First, the face region is detected through spatial pyramid pooling and a multi-scale feature output module. Then, a multi-scale facial landmark detector is used to locate 23 key points on the face. The aspect ratios of the eyes and mouth are calculated based on the coordinates of these key points, and a feature parameter matrix for fatigue driving recognition is obtained. Finally, the feature parameter matrix is converted into an image, and the residual Swin Transformer network is presented to recognize fatigue driving. Experimental results on the HNUFD dataset show that the proposed method achieves an accuracy of 96.512%, thus outperforming state-of-the-art methods. Full article

Detecting drowsiness among drivers is critical for ensuring road safety and preventing accidents caused by drowsy or fatigued driving. Research on yawn detection among drivers has great significance in improving traffic safety. Although various studies have taken place where deep learning-based approaches are being proposed, there is still room for improvement to develop better and more accurate drowsiness detection systems using behavioral features such as mouth and eye movement. This study proposes a deep neural network architecture for drowsiness detection employing a convolutional neural network (CNN) for driver drowsiness detection. Experiments involve using the DLIB library to locate key facial points to calculate the mouth aspect ratio (MAR). To compensate for the small dataset, data augmentation is performed for the ‘yawning’ and ‘no_yawning’ classes. Models are trained and tested involving the original and augmented dataset to analyze the impact on model performance. Experimental results demonstrate that the proposed CNN model achieves an average accuracy of 96.69%. Performance comparison with existing state-of-the-art approaches shows better performance of the proposed model. Full article

In response to negative impacts such as personal and property safety hazards caused by drivers being distracted while driving on the road, this article proposes a driver’s attention state-detection method based on the improved You Only Look Once version five (YOLOv5). Both fatigue and distracted behavior can cause a driver’s attention to be diverted during the driving process. Firstly, key facial points of the driver are located, and the aspect ratio of the eyes and mouth is calculated. Through the examination of relevant information and repeated experimental verification, threshold values for the aspect ratio of the eyes and mouth under fatigue conditions, corresponding to closed eyes and yawning, are established. By calculating the aspect ratio of the driver’s eyes and mouth, it is possible to accurately detect whether the driver is in a state of fatigue. Secondly, distracted abnormal behavior is detected using an improved YOLOv5 model. The backbone network feature extraction element is modified by adding specific modules to obtain different receptive fields through multiple convolution operations on the input feature map, thereby enhancing the feature extraction ability of the network. The introduction of Swin Transformer modules in the feature fusion network replaces the Bottleneck modules in the C3 module, reducing the computational complexity of the model while increasing its receptive field. Additionally, the network connection in the feature fusion element has been modified to enhance its ability to fuse information from feature maps of different sizes. Three datasets were created of distracting behaviors commonly observed during driving: smoking, drinking water, and using a mobile phone. These datasets were used to train and test the model. After testing, the mAP (mean average precision) has improved by 2.4% compared to the model before improvement. Finally, through comparison and ablation experiments, the feasibility of this method has been verified, which can effectively detect fatigue and distracted abnormal behavior. Full article

Traffic command and scheduling are the core monitoring aspects of railway transportation. Detecting the fatigued state of dispatchers is, therefore, of great significance to ensure the safety of railway operations. In this paper, we present a multi-feature fatigue detection method based on key points of the human face and body posture. Considering unfavorable factors such as facial occlusion and angle changes that have limited single-feature fatigue state detection methods, we developed our model based on the fusion of body postures and facial features for better accuracy. Using facial key points and eye features, we calculate the percentage of eye closure that accounts for more than 80% of the time duration, as well as blinking and yawning frequency, and we analyze fatigue behaviors, such as yawning, a bowed head (that could indicate sleep state), and lying down on a table, using a behavior recognition algorithm. We fuse five facial features and behavioral postures to comprehensively determine the fatigue state of dispatchers. The results show that on the 300 W dataset, as well as a hand-crafted dataset, the inference time of the improved facial key point detection algorithm based on the retina–face model was 100 ms and that the normalized average error (NME) was 3.58. On our own dataset, the classification accuracy based the an Bi-LSTM-SVM adaptive enhancement algorithm model reached 97%. Video data of volunteers who carried out scheduling operations in the simulation laboratory were used for our experiments, and our multi-feature fusion fatigue detection algorithm showed an accuracy rate of 96.30% and a recall rate of 96.30% in fatigue classification, both of which were higher than those of existing single-feature detection methods. Our multi-feature fatigue detection method offers a potential solution for fatigue level classification in vital areas of the industry, such as in railway transportation. Full article

The 3D quantitative analysis of facial morphology is of importance in plastic surgery (PS), which could help surgeons design appropriate procedures before conducting the surgery. We propose a system to simulate and guide the shaping effect analysis, which could produce a similar but more harmonious face simulation. To this end, first, the depth camera based on structured light coding is employed for facial 3D data acquisition, from which the point cloud data of multiple facial perspectives could be obtained. Next, the cascade regression tree algorithm is used to extract the esthetic key points of the face model and to calculate the facial features composed of the key points, such as the nose, chin, and eyes. Quantitative facial esthetic indexes are offered to doctors to simulate PS. Afterward, we exploit a face mesh metamorphosis based on finite elements. We design several morphing operators, including augmentation, cutting, and lacerating. Finally, the regional deformation is detected, and the operation effect is quantitatively evaluated by registering the 3D scanning model before and after the operation. The test of our proposed system and the simulation of PS operations find that the measurement error of facial geometric features is 0.458 mm, and the area is 0.65 mm². The ratings of the simulation outcomes provided by panels of PS prove that the system is effective. The manipulated 3D faces are deemed more beautiful compared to the original faces respecting the beauty canons such as facial symmetry and the golden ratio. The proposed algorithm could generate realistic visual effects of PS simulation. It could thus assist the preoperative planning of facial PS. Full article